Emergent Properties of Foveated Perceptual Systems

人工智能 计算机科学 人类视觉系统模型 计算机视觉 稳健性(进化) 卷积神经网络 视觉感受 感知 模式识别(心理学) 图像(数学) 生物化学 化学 神经科学 生物 基因
作者
Arturo Deza,Talia Konkle
摘要

We introduce foveated perceptual systems -- a hybrid architecture inspired by human vision, to explore the role of a \textit{texture-based} foveation stage on the nature and robustness of subsequently learned visual representation in machines. Specifically, these two-stage perceptual systems first foveate an image, inducing a texture-like encoding of peripheral information -- mimicking the effects of \textit{visual crowding} -- which is then relayed through a convolutional neural network (CNN) trained to perform scene categorization. We find that these foveated perceptual systems learn a visual representation that is \textit{distinct} from their non-foveated counterpart through experiments that probe: 1) i.i.d and o.o.d generalization; 2) robustness to occlusion; 3) a center image bias; and 4) high spatial frequency sensitivity. In addition, we examined the impact of this foveation transform with respect to two additional models derived with a rate-distortion optimization procedure to compute matched-resource systems: a lower resolution non-foveated system, and a foveated system with adaptive Gaussian blurring. The properties of greater i.i.d generalization, high spatial frequency sensitivity, and robustness to occlusion emerged exclusively in our foveated texture-based models, independent of network architecture and learning dynamics. Altogether, these results demonstrate that foveation -- via peripheral texture-based computations -- yields a distinct and robust representational format of scene information relative to standard machine vision approaches, and also provides symbiotic computational support that texture-based peripheral encoding has important representational consequences for processing in the human visual system.

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
2秒前
3秒前
研友_VZG7GZ应助欣喜沛芹采纳,获得10
4秒前
感动黄豆完成签到,获得积分20
5秒前
6秒前
6秒前
8秒前
10秒前
Owen应助Kikua采纳,获得10
10秒前
juliar完成签到 ,获得积分10
10秒前
11秒前
Bressanone发布了新的文献求助10
11秒前
12秒前
彭于晏应助忐忑的阑香采纳,获得10
12秒前
赘婿应助xiaojian_291采纳,获得10
12秒前
13秒前
郭小宝发布了新的文献求助20
13秒前
糊涂的语兰完成签到,获得积分10
14秒前
浮生若梦完成签到 ,获得积分10
15秒前
CA发布了新的文献求助10
15秒前
忘记时间发布了新的文献求助30
15秒前
王羊补牢完成签到,获得积分10
17秒前
18秒前
潇湘雪月发布了新的文献求助10
23秒前
栗园应助仙都丽娜采纳,获得10
24秒前
严珍珍完成签到 ,获得积分10
24秒前
思源应助郭小宝采纳,获得10
24秒前
无理完成签到 ,获得积分10
25秒前
27秒前
27秒前
无端完成签到 ,获得积分20
27秒前
感动黄豆发布了新的文献求助10
28秒前
量子星尘发布了新的文献求助10
28秒前
29秒前
zwy109发布了新的文献求助10
30秒前
32秒前
立夏完成签到,获得积分10
33秒前
33秒前
34秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3989242
求助须知:如何正确求助?哪些是违规求助? 3531393
关于积分的说明 11253753
捐赠科研通 3270010
什么是DOI,文献DOI怎么找? 1804868
邀请新用户注册赠送积分活动 882084
科研通“疑难数据库(出版商)”最低求助积分说明 809136